Implicit Generation and Generalization Methods for Energy-Based Models

Energy-based models represent probability distributions over data by assigning an unnormalized probability scalar (or “energy”) to each input data point. The combination of EBMs and iterative refinement have the following benefits:

We found energy-based models are able to generate qualitatively and quantitatively high-quality images, especially when running the refinement process for a longer period at test time. By combining the resultant energy-based models, we were able to generate different size shapes at different locations, despite never seeing examples of both being changed.

Source: openai.com